Automobile financial customer behavior data analysis method and system based on artificial intelligence

Abstract

The invention discloses an automobile financial customer behavior data analysis method based on artificial intelligence, and relates to the technical field of data processing, and the method comprises the steps: obtaining behavior data of a transacted automobile financial customer based on an artificial intelligence terminal, obtaining a transacted automobile financial service, obtaining an automobile financial demand, and generating a feature dimension; obtaining first behavior data, second behavior data and third behavior data; obtaining a first feature value, a second feature value and a third feature value based on a feature calculation model; and obtaining a feature trend index corresponding to each feature dimension according to the first feature value, the second feature value and the third feature value corresponding to each feature dimension, and obtaining a push relationship between the automobile financial service and the behavior data according to each feature trend index. The invention further provides an automobile financial customer behavior data analysis system based on artificial intelligence. The method has the advantages that dynamic trend analysis is achieved, the analysis effect is good, and accurate prediction pushing is planned to be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an automobile finance customer behavior data analysis method and system based on artificial intelligence. Background Art

[0002] In today's highly digital financial market environment, auto finance services have become an important bridge between automakers, dealers and consumers. However, with the intensification of market competition and the diversification of customer needs, how to accurately capture and respond to customers' dynamic needs and preference changes has become a key challenge for auto finance service providers.

[0003] Existing methods for analyzing automobile finance customer behavior data often focus on static automobile finance customer portraits and financial behavior analysis, and only pay attention to data at a single point in time, ignoring changes and trends in customer behavior data over time. This static analysis method cannot fully reflect customers' dynamic needs and preference changes, and therefore limits the potential for optimizing financial services. In other words, although these methods can provide certain customer insights, they cannot fully reflect customers' dynamic needs and preference changes. This limitation leads to obvious deficiencies in financial service providers in predicting customers' future behavior and pushing precise services. Therefore, when new customers exhibit similar or identical behavioral characteristics to existing customers, these methods often cannot accurately identify and push corresponding automobile financial services. Summary of the invention

[0004] In view of the defects in the prior art, the present invention provides an automobile finance customer behavior data analysis method and system based on artificial intelligence.

[0005] An artificial intelligence-based automobile finance customer behavior data analysis method comprises: obtaining behavior data of completed automobile finance customers based on an artificial intelligence terminal, and obtaining completed automobile finance services based on the behavior data, and obtaining multiple automobile finance demands based on the completed automobile finance services, and generating multiple feature dimensions based on the multiple automobile finance demands; obtaining first behavior data, second behavior data, and third behavior data distributed in chronological order based on the behavior data; obtaining first feature values ​​corresponding to each feature dimension based on a feature calculation model and the first behavior data, obtaining second feature values ​​corresponding to each feature dimension based on the feature calculation model and the second behavior data, and obtaining third feature values ​​corresponding to each feature dimension based on the feature calculation model and the third behavior data; obtaining feature trend indicators corresponding to each feature dimension based on the first feature value, the second feature value, and the third feature value corresponding to each feature dimension, and obtaining a push relationship between automobile finance services and behavior data based on each feature trend indicator.

[0006] Preferably, obtaining the characteristic trend corresponding to each characteristic dimension according to the first eigenvalue, the second eigenvalue and the third eigenvalue corresponding to each characteristic dimension includes: obtaining the first difference amount corresponding to the i-th characteristic dimension according to the first eigenvalue and the third eigenvalue corresponding to the i-th characteristic dimension, the first difference amount is equal to the third eigenvalue minus the first eigenvalue; obtaining the second difference amount corresponding to the i-th characteristic dimension according to the second eigenvalue and the third eigenvalue corresponding to the i-th characteristic dimension, the second difference amount is equal to the third eigenvalue minus the second eigenvalue; obtaining the characteristic trend indicator corresponding to the i-th characteristic dimension according to the first difference amount, the second difference amount and the third eigenvalue.

[0007] Preferably, the characteristic trend index corresponding to the i-th characteristic dimension is obtained according to the first difference amount, the second difference amount and the third characteristic value and is expressed as: i =(ΔC i1 +ΔC i2 )·C i3 ; Among them, T i is the characteristic trend indicator corresponding to the i-th characteristic dimension, ΔC i1 is the first difference corresponding to the i-th feature dimension, ΔC i2 is the second difference corresponding to the i-th feature dimension, C i3 is the third eigenvalue corresponding to the i-th feature dimension.

[0008] Preferably, the feature calculation model in which the first feature value corresponding to each feature dimension is obtained based on the feature calculation model and the first behavior data is expressed as: i1 =α i1 ·(ln(l i1 +γ)+t i1 ), where C i1 is the first eigenvalue of the i-th feature dimension, α i1 is the adjustment coefficient of the i-th feature dimension in the first line of data, l i1 is the number of clicks on the i-th feature dimension in the first behavior data, t i1 is the browsing time of the i-th feature dimension in the first line of data, and γ is a preset parameter.

[0009] Preferably, the feature calculation model in which the second feature value corresponding to each feature dimension is obtained based on the feature calculation model and the second behavior data is expressed as: i2 =α i2 ·(ln(l i2 +γ)+t i2 ), where C i2 is the second eigenvalue of the i-th feature dimension, α i2 is the adjustment coefficient of the i-th feature dimension in the second line of data, l i2is the number of clicks on the i-th feature dimension in the second behavior data, t i2 is the browsing time of the i-th feature dimension in the second behavior data, and γ is a preset parameter.

[0010] Preferably, the feature calculation model in which the third feature value corresponding to each feature dimension is obtained based on the feature calculation model and the third behavior data is expressed as: i3 =α i3 ·(ln(l i3 +γ)+t i3 ), where C i3 is the third eigenvalue of the i-th feature dimension, α i3 is the adjustment coefficient of the i-th feature dimension in the third line of data, l i3 is the number of clicks on the i-th feature dimension in the third behavior data, t i3 is the browsing time of the i-th feature dimension in the third behavior, and γ is a preset parameter.

[0011] Preferably, obtaining first behavior data, second behavior data and third behavior data distributed in chronological order based on the behavior data includes: obtaining the behavior start time point, the middle time point of the first behavior, the middle time point of the second behavior and the behavior end time point distributed in chronological order based on the behavior data; obtaining a first time period based on the behavior start time point and the middle time point of the first behavior, and obtaining the first behavior data corresponding to the first time period; obtaining a second time period based on the middle time point of the first behavior and the middle time point of the second behavior, and obtaining the second behavior data corresponding to the second time period; obtaining a third time period based on the middle time point of the second behavior and the behavior end time point, and obtaining the third behavior data corresponding to the third time period.

[0012] Preferably, obtaining first behavior data, second behavior data, and third behavior data distributed in chronological order based on the behavior data includes: obtaining a time series based on the behavior data and setting a first time window; obtaining a first time period, a second time period, and a third time period distributed in chronological order on the behavior time series based on the first time window; obtaining first behavior data corresponding to the first time period, second behavior data corresponding to the second time period, and third behavior data corresponding to the third time period based on the behavior data.

[0013] A car finance customer behavior data analysis system based on artificial intelligence is also provided. The system is used to implement a car finance customer behavior data analysis method based on artificial intelligence. The system includes: an acquisition and generation module, which is used to acquire the behavior data of completed car finance customers based on an artificial intelligence terminal, and acquire completed car finance services based on the behavior data, and acquire multiple car finance needs based on the completed car finance services, and generate multiple feature dimensions based on the multiple car finance needs; a data acquisition module, which is used to acquire first behavior data, second behavior data, and third behavior data distributed in chronological order based on the behavior data; a feature calculation module, which is used to acquire a first feature value corresponding to each feature dimension based on a feature calculation model and the first behavior data, acquire a second feature value corresponding to each feature dimension based on the feature calculation model and the second behavior data, and acquire a third feature value corresponding to each feature dimension based on the feature calculation model and the third behavior data; an analysis and processing module, which is used to acquire a feature trend indicator corresponding to each feature dimension based on the first feature value, the second feature value, and the third feature value corresponding to each feature dimension, and acquire a push relationship between the car finance service and the behavior data based on each feature trend indicator.

[0014] An electronic device is also provided, comprising: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the above-mentioned automobile finance customer behavior data analysis method based on artificial intelligence.

[0015] The beneficial effects of the present invention are embodied in:

[0016] In the entire AI-based auto finance customer behavior data analysis method, the dynamic behavior data of completed customers is captured and analyzed through AI-based terminals, which not only breaks through the limitations of traditional static analysis, but also fully reflects the dynamic changes in customer needs and preference trends; further, by decomposing and deeply processing customer behavior data in the time dimension, combined with feature calculation models, it can accurately capture changes in customer attention and preference shifts in various financial service attributes; further, by using these refined data to construct feature trend indicators, financial service providers can more accurately predict customers' future behavior, thereby achieving accurate push of personalized services, which not only improves marketing efficiency and reduces operating costs, but also shows significant results in improving customer experience and enhancing customer stickiness. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0018] Figure 1 A schematic diagram of the steps of the method for analyzing automobile finance customer behavior data based on artificial intelligence of the present invention;

[0019] Figure 2 This is a schematic diagram of step S4 in the automobile finance customer behavior data analysis method based on artificial intelligence of the present invention;

[0020] Figure 3 This is a schematic diagram of the steps of S2 in one embodiment of the automobile finance customer behavior data analysis method based on artificial intelligence of the present invention;

[0021] Figure 4 This is a schematic diagram of steps of S2 in another implementation of the method for analyzing automobile finance customer behavior data based on artificial intelligence of the present invention;

[0022] Figure 5 The present invention is a block diagram of an electronic device according to an embodiment of the present invention.

[0023] Reference numerals:

[0024] 700 - electronic device, 701 - processor, 702 - memory, 703 - multimedia component, 704 - input / output (I / O) interface, 705 - communication component. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0026] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. In addition, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0028] like Figure 1As shown, a method for analyzing automobile finance customer behavior data based on artificial intelligence is provided, including:

[0029] S1. Obtaining behavioral data of completed auto finance customers based on an artificial intelligence terminal, and obtaining completed auto finance services based on the behavioral data, and obtaining multiple auto finance needs based on the completed auto finance services, and generating multiple feature dimensions based on the multiple auto finance needs;

[0030] S2. acquiring first behavior data, second behavior data, and third behavior data distributed in chronological order according to the behavior data;

[0031] S3, acquiring first eigenvalues ​​corresponding to each feature dimension based on the feature calculation model and the first behavior data, acquiring second eigenvalues ​​corresponding to each feature dimension based on the feature calculation model and the second behavior data, and acquiring third eigenvalues ​​corresponding to each feature dimension based on the feature calculation model and the third behavior data;

[0032] S4. Obtain a characteristic trend index corresponding to each characteristic dimension according to the first characteristic value, the second characteristic value, and the third characteristic value corresponding to each characteristic dimension, and obtain a push relationship between the automobile financial service and the behavior data according to each characteristic trend index.

[0033] In this embodiment, it should be noted that in S1, the behavioral data of the completed auto finance customers are captured and analyzed through the artificial intelligence terminal; the artificial intelligence terminal here refers to an integrated artificial intelligence technology that can capture and analyze various data, including the behavioral data of the completed auto finance customers; the "completed auto finance service" here specifically refers to the financial services that the customer has accepted and is using, such as vehicle purchase loan services, vehicle leasing services or vehicle insurance services; taking the vehicle purchase loan service as an example, this type of service involves multiple aspects of auto finance needs, including loan repayment period, loan interest rate, loan repayment method and early repayment conditions. Further, these auto finance needs are converted into quantifiable feature dimensions; the feature dimensions here serve as a quantitative benchmark for data processing, so that the originally complex and diverse customer needs can be systematically classified and compared. For example, "loan repayment period" can be used as a feature dimension to quantify the customer's preference for the loan period; "loan interest rate" is another feature dimension, reflecting the customer's sensitivity to the loan cost.

[0034] In S2, customer behavior data is broken down and analyzed in chronological order. Specifically, it not only focuses on the customer's behavior at a specific point in time, but also tracks the evolution of customer behavior data on the timeline; by obtaining the first behavior data, second behavior data, and third behavior data distributed in chronological order, it can capture the dynamic changes in customer needs and preference trends.

[0035] Take an auto finance customer as an example. In S2, the customer's behavior data at different time points are collected and analyzed. In the early stage, when browsing financial services, the customer pays more attention to the loan interest rate and loan term of Class A products, the process and required materials of Class A' products, and the early repayment information of A", etc.; in the middle stage, as the understanding deepens, the customer pays more attention to the loan interest rate and loan term of Class B products, the process and required materials of Class B' products, and the early repayment information of B", etc.; in the later stage, the customer pays more attention to the loan interest rate and loan term of Class C products, the process and required materials of Class C' products, and the early repayment information of C", etc.

[0036] In S3, the feature calculation model is used to deeply process customer behavior data at different time points. Specifically, it first obtains the first feature values ​​corresponding to each feature dimension (such as loan repayment period, loan interest rate, etc.) based on the first behavior data through the feature calculation model. These first feature values ​​actually reflect the customer's attention and preference for various auto financial service attributes in the initial stage; then, the second and third behavior data are processed in the same way to obtain the second and third feature values ​​respectively. The changes in these feature values ​​not only reveal the dynamic evolution of customer needs, but also provide a data basis for subsequent analysis of customer behavior trends and prediction of future needs.

[0037] Take the behavior data of a specific customer as an example. Under the characteristic dimension of loan interest rate, the customer shows a high degree of concern for the characteristic dimension of loan interest rate of Class A products in the early stage (first behavior data), and the corresponding first characteristic value corresponds to the value of loan interest rate of Class A products; as time goes by, in the middle stage (second behavior data), the customer shows a high degree of concern for the characteristic dimension of loan interest rate of Class B products, and the corresponding first characteristic value corresponds to the value of loan interest rate of Class B products; and in the later stage (third behavior data), the customer shows a high degree of concern for the characteristic dimension of loan interest rate of Class C products, and the corresponding first characteristic value corresponds to the value of loan interest rate of Class C products. Through the changes in this series of characteristic values ​​(i.e., loan interest rate values), we can clearly observe the shift and deepening of customers' demand for financial services at different stages. Generally speaking, customers' requirements for loan interest rates must be as low as possible, but the lower the loan interest rate, the higher the eigenvalues ​​of other characteristic dimensions (for example, the higher the credit requirement, the lower the application approval rate, or the higher the early repayment time limit). Therefore, based on the customer's own conditions and comprehensive needs, the eigenvalue of the characteristic dimension of loan interest rate may decrease, increase or fluctuate. Therefore, the first eigenvalue, second eigenvalue and third eigenvalue are generated to facilitate subsequent trend analysis.

[0038] In summary, S3 has achieved refined processing of customer behavior data in the time dimension by introducing a feature calculation model, which not only improves the accuracy and depth of data analysis, but also enables financial service providers to more keenly capture the dynamic changes in customer needs.

[0039] In S4, based on the data obtained in the previous steps, analysis is performed to reveal the dynamic trend of customer behavior. Specifically, according to the first eigenvalue, the second eigenvalue and the third eigenvalue corresponding to each characteristic dimension calculated in S3, the change trend of these eigenvalues ​​on the time axis is further analyzed to obtain the characteristic trend indicators corresponding to each characteristic dimension; these indicators not only reflect the customer's continued attention to a certain financial service attribute, but also reveal the direction and speed of change of their preferences.

[0040] Assume that in S3, three characteristic values ​​of a customer on the characteristic dimension of "loan repayment period" are obtained, the first characteristic value is 5 years in the initial stage, the second characteristic value is 7 years, and the third characteristic value is 10 years. In S4, an upward trend line can be drawn based on these three characteristic values. This is the characteristic trend indicator of the customer on the dimension of "loan repayment period", which shows that over time, the customer is more and more inclined to choose longer-term loan services; in this way, characteristic trend indicators of multiple characteristic dimensions are obtained. When a new customer appears, the customer's behavior data is analyzed. If it is the same or similar to the characteristic trend indicator in S4, the auto financial service that has been completed in S1 is directly pushed. And based on big data and artificial intelligence terminals, a large number of different auto financial services that have been completed can be processed in parallel at the same time, so as to achieve more comprehensive personalized service push.

[0041] To sum up, in the entire AI-based automobile finance customer behavior data analysis method, the dynamic behavior data of completed customers is captured and analyzed through AI-based terminals, which not only breaks through the limitations of traditional static analysis, but also fully reflects the dynamic changes in customer needs and preference trends; further, by decomposing and deeply processing customer behavior data in the time dimension, combined with feature calculation models, it is possible to accurately capture changes in customer attention and preference shifts in various financial service attributes; further, by using these refined data to construct feature trend indicators, financial service providers can more accurately predict customers' future behavior, thereby achieving accurate push of personalized services, which not only improves marketing efficiency and reduces operating costs, but also shows significant results in improving customer experience and enhancing customer stickiness.

[0042] like Figure 2 As shown, in one embodiment, obtaining the characteristic trend corresponding to each characteristic dimension according to the first characteristic value, the second characteristic value, and the third characteristic value corresponding to each characteristic dimension in S4 includes:

[0043] S41, obtaining a first difference amount corresponding to the i-th feature dimension according to the first eigenvalue and the third eigenvalue corresponding to the i-th feature dimension, where the first difference amount is equal to the third eigenvalue minus the first eigenvalue;

[0044] S42, obtaining a second difference amount corresponding to the i-th feature dimension according to the second eigenvalue and the third eigenvalue corresponding to the i-th feature dimension, where the second difference amount is equal to the third eigenvalue minus the second eigenvalue;

[0045] S43. Obtain a characteristic trend indicator corresponding to the i-th characteristic dimension according to the first difference amount, the second difference amount and the third characteristic value.

[0046] In this embodiment, it should be noted that, in S41, the first difference between the first eigenvalue and the third eigenvalue in each feature dimension is calculated, and this difference actually reflects the changes in customer needs or preferences from the initial stage to the later stage in each feature dimension; this method of calculating the difference is not only simple and intuitive, but also can quantify the degree of change in customer needs; at the same time, the use of the first eigenvalue and the third eigenvalue can capture the overall change in customer behavior from the initial stage to the later stage, and this change usually represents the long-term trend or preference shift of customers.

[0047] In S42, similarly, the second difference between the second eigenvalue and the third eigenvalue in each characteristic dimension is calculated. This difference actually reflects the changes in customer demand or preference from the mid-term to the late stage in each characteristic dimension. This method of calculating the difference is also simple and intuitive, and can quantify the degree of change in customer demand. Using the second eigenvalue and the third eigenvalue to calculate the second difference can capture short-term fluctuations.

[0048] In S43, based on the first difference amount and the second difference amount calculated previously, combined with the third eigenvalue, the characteristic trend index corresponding to each characteristic dimension is comprehensively obtained, in order to more comprehensively analyze the changing trend of the customer behavior data on the time axis, so as to more accurately predict the customer's future needs. Specifically, the third eigenvalue represents the customer's latest behavior data during the observation period, so constructing a characteristic trend index based on it can more accurately reflect the customer's current preferences and demand status; by comprehensively considering these difference amounts and the third eigenvalue, a comprehensive characteristic trend index can be obtained, which not only reflects the long-term demand change trend of the customer, but also includes the recent demand fluctuations.

[0049] In one embodiment, the characteristic trend index corresponding to the i-th characteristic dimension is obtained according to the first difference amount, the second difference amount and the third characteristic value in S43 and is expressed as:

[0050] Ti =(ΔC i1 +ΔC i2 )·C i3 ;in,

[0051] T i is the characteristic trend indicator corresponding to the i-th characteristic dimension, ΔC i1 is the first difference corresponding to the i-th feature dimension, ΔC i2 is the second difference corresponding to the i-th feature dimension, C i3 is the third eigenvalue corresponding to the i-th feature dimension.

[0052] In this embodiment, it should be noted that the expression aims to capture the long-term trend, medium-term fluctuation and latest status of customer demand by combining the first difference amount, the second difference amount and the third eigenvalue, so as to provide enterprises with more accurate market forecasts and decision-making support.

[0053] Furthermore, the push relationship between automobile financial services and behavior data is obtained based on each characteristic trend indicator. i >0, due to C i3 >0, then ΔC i1 +ΔC i2 >0, which means that the transaction customer behavior is increasing in the i-th feature dimension (such as loan interest rate increase). i >0, due to C i3 >0, then ΔC i1 +ΔC i2 >0, which means that the behavior of the completed customer is reduced in the i-th feature dimension (for example, the loan term is shortened). The calculated T i The absolute value of represents the target range level of the completed customer on the i-th feature dimension, T i The larger the absolute value of, the higher the target range level, T i The smaller the absolute value of is, the smaller the target range level is. The corresponding relationship between the two is obtained based on historical data or expert experience. For example, T i The absolute value represents a mid-range loan interest rate of 5% to 10%.

[0054] When the new customer behavior is consistent with the behavior trend of the existing customer in the i-th feature dimension (increase / decrease), and the new customer behavior also falls within the target range level of the existing customer, the push condition is met in the i-th feature dimension. When multiple (or all) feature dimensions meet the above conditions, the completed auto financial service in S1 is pushed to the new customer.

[0055] In one embodiment, the feature calculation model in S3 in which the first feature value corresponding to each feature dimension is obtained based on the feature calculation model and the first behavior data is expressed as:

[0056] C i1 =α i1 ·(ln(l i1 +γ)+t i1 );in,

[0057] C i1 is the first eigenvalue of the i-th feature dimension, α i1 is the adjustment coefficient of the i-th feature dimension in the first line of data, l i1 is the number of clicks on the i-th feature dimension in the first behavior data, t i1 is the browsing time of the i-th feature dimension in the first line of data, and γ is a preset parameter.

[0058] Similarly, the feature calculation model in S3 for obtaining the second feature value corresponding to each feature dimension based on the feature calculation model and the second behavior data is expressed as:

[0059] C i2 =α i2 ·(ln(l i2 +γ)+t i2 );in,

[0060] C i2 is the second eigenvalue of the i-th feature dimension, α i2 is the adjustment coefficient of the i-th feature dimension in the second line of data, l i2 is the number of clicks on the i-th feature dimension in the second behavior data, t i2 is the browsing time of the i-th feature dimension in the second behavior data, and γ is a preset parameter.

[0061] Similarly, the feature calculation model in S3 for obtaining the third feature value corresponding to each feature dimension based on the feature calculation model and the third behavior data is expressed as:

[0062] C i3 =α i3 ·(ln(l i3 +γ)+t i3 );in,

[0063] C i3 is the third eigenvalue of the i-th feature dimension, α i3 is the adjustment coefficient of the i-th feature dimension in the third line of data, l i3 is the number of clicks on the i-th feature dimension in the third behavior data, t i3 is the browsing time of the i-th feature dimension in the third behavior, and γ is a preset parameter.

[0064] In this embodiment, it should be noted that the same characteristic calculation model is used in the calculation of the first eigenvalue, the second eigenvalue and the third eigenvalue. i1 +γ)、ln(l i2 +γ) or ln(l i3 +γ) respectively processes the click volume of the i-th feature dimension in the first behavior data, the second behavior data, or the third behavior data. This can compress the range of click volume, especially when the click volume is very large, which helps to reduce the impact of extreme values ​​on the model. Secondly, it can give a lower click volume a greater weight change, which can effectively solve the current situation of uneven distribution of click volume data or long-tail distribution. Further, the browsing time t i1 ,t i2 or i3 Linearly adding α to the model means that the user's stay time on the i-th feature dimension is directly considered. The browsing time is usually regarded as the user's interest or importance in the feature. Furthermore, by introducing the adjustment coefficient α i1 , α i2 or α i3 , the model allows flexible weight adjustment of different feature dimensions at different time stages (i.e., first-behavior data, second-behavior data, and third-behavior data), which is very useful for dealing with the importance differences between different features or for feature selection.

[0065] like Figure 3 As shown, in one embodiment, S2 includes:

[0066] S21, obtaining, according to the behavior data, a behavior start time point, a first behavior middle time point, a second behavior middle time point, and a behavior end time point distributed in chronological order;

[0067] S22, obtaining a first time period according to the behavior start time point and the middle time point of the first behavior, and obtaining first behavior data corresponding to the first time period;

[0068] Acquire a second time period according to the middle time point of the first behavior and the middle time point of the second behavior, and acquire the second behavior data corresponding to the second time period;

[0069] A third time period is obtained according to the middle time point of the second behavior and the end time point of the behavior, and third behavior data corresponding to the third time period is obtained.

[0070] In this embodiment, it should be noted that in S21, based on the collected behavioral data, key time points are identified and extracted, including the start time point of the behavior, the middle time point of the first behavior, the middle time point of the second behavior, and the end time point of the behavior. These time points are arranged in the order of actual occurrence, providing a basis for the subsequent time period division.

[0071] In S22, based on the time points extracted in S21, the entire behavior process is divided into three time periods: a first time period (from the behavior start time point to the middle time point of the first behavior), a second time period (from the middle time point of the first behavior to the middle time point of the second behavior), and a third time period (from the middle time point of the second behavior to the behavior end time point). Subsequently, the corresponding behavior data in these three time periods are extracted, namely, the first behavior data, the second behavior data, and the third behavior data.

[0072] In summary, by breaking down the behavior process into multiple time periods, we can gain a deeper understanding of users’ behavior patterns and preferences at different stages. This refined analysis method helps discover subtle changes in user behavior and provides strong support for optimizing product design and services.

[0073] like Figure 4 As shown, in one embodiment, S2 includes:

[0074] S201, obtaining a time series according to the behavior data and setting a first time window;

[0075] S202, acquiring a first time period, a second time period, and a third time period distributed in chronological order on the behavior time series according to the first time window;

[0076] S203. Acquire, according to the behavior data, first behavior data corresponding to the first time period, second behavior data corresponding to the second time period, and third behavior data corresponding to the third time period.

[0077] In this embodiment, it should be noted that in S201, a complete time series is first obtained based on the collected behavioral data. This time series records the sequence and time points of the user's behaviors. Then a first time window is set. The size of this window can be adjusted according to actual needs to determine the granularity of the subsequent time period division.

[0078] In S202, the set first time window is used to slide on the behavior time series, thereby dividing three time periods distributed in chronological order: the first time period, the second time period and the third time period. This division method ensures that the behavior data in each time period is continuous and consistent in time, which is convenient for subsequent analysis and comparison.

[0079] In S203, according to the divided time periods, the behavior data corresponding to each time period is extracted from the original behavior data. Specifically, the first behavior data corresponding to the first time period, the second behavior data corresponding to the second time period, and the third behavior data corresponding to the third time period are obtained respectively. These data sets provide a basis for subsequent feature extraction, etc.

[0080] In summary, by setting and adjusting the size of the first time window, the granularity of time period division can be flexibly controlled to meet the data analysis needs in different scenarios; the time periods are divided in chronological order and the corresponding behavior data are extracted to ensure the accuracy and timeliness of data processing. The data in each time period has clear boundaries and continuity in time, which helps to reduce errors and deviations in data analysis.

[0081] An automobile finance customer behavior data analysis system based on artificial intelligence is also provided. The system is used to implement the automobile finance customer behavior data analysis method based on artificial intelligence in any one of the above embodiments. The system includes:

[0082] An acquisition and generation module is used to acquire the behavior data of completed auto finance customers based on an artificial intelligence terminal, and acquire completed auto finance services based on the behavior data, and acquire multiple auto finance demands based on the completed auto finance services, and generate multiple feature dimensions based on the multiple auto finance demands;

[0083] A data acquisition module, used for acquiring first behavior data, second behavior data and third behavior data distributed in chronological order according to the behavior data;

[0084] A feature calculation module, used to obtain a first feature value corresponding to each feature dimension based on the feature calculation model and the first behavior data, obtain a second feature value corresponding to each feature dimension based on the feature calculation model and the second behavior data, and obtain a third feature value corresponding to each feature dimension based on the feature calculation model and the third behavior data;

[0085] The analysis and processing module is used to obtain the characteristic trend index corresponding to each characteristic dimension according to the first characteristic value, the second characteristic value and the third characteristic value corresponding to each characteristic dimension, and obtain the push relationship between the automobile financial service and the behavior data according to each characteristic trend index.

[0086] In this embodiment, it should be noted that, regarding the above-mentioned artificial intelligence-based automobile finance customer behavior data analysis system, the specific method of performing operations therein has been described in detail in the implementation of the artificial intelligence-based automobile finance customer behavior data analysis method, and will not be elaborated here.

[0087] Figure 5is a block diagram of an electronic device showing an artificial intelligence-based automobile finance customer behavior data analysis method according to an exemplary embodiment. Figure 5 As shown, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0088] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned artificial intelligence-based automobile financial customer behavior data analysis method. The memory 702 is used to store various types of data to support the operation of the electronic device 700, and these data may include, for example, instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0089] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned artificial intelligence-based automobile finance customer behavior data analysis method.

[0090] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned method for analyzing automobile finance customer behavior data based on artificial intelligence are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions may be executed by the processor 701 of the electronic device 700 to complete the above-mentioned method for analyzing automobile finance customer behavior data based on artificial intelligence.

[0091] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned artificial intelligence-based automobile finance customer behavior data analysis method when executed by the programmable device.

[0092] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0093] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0094] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. An artificial intelligence-based automobile finance customer behavior data analysis method, characterized in that: include: Based on the artificial intelligence terminal, the behavioral data of the completed auto finance customers are obtained, and the completed auto finance services are obtained based on the behavioral data, and multiple auto finance needs are obtained based on the completed auto finance services, and multiple feature dimensions are generated based on the multiple auto finance needs; Acquire first behavior data, second behavior data, and third behavior data distributed in chronological order according to the behavior data; Acquire first eigenvalues ​​corresponding to each eigendimension based on the eigencal model and the first behavior data, acquire second eigenvalues ​​corresponding to each eigendimension based on the eigencal model and the second behavior data, and acquire third eigenvalues ​​corresponding to each eigendimension based on the eigencal model and the third behavior data; The characteristic trend index corresponding to each characteristic dimension is obtained according to the first characteristic value, the second characteristic value and the third characteristic value corresponding to each characteristic dimension, and the push relationship between the automobile financial service and the behavior data is obtained according to each characteristic trend index.

2. The method for analyzing automobile finance customer behavior data based on artificial intelligence according to claim 1, characterized in that: The acquiring of the characteristic trend corresponding to each characteristic dimension according to the first characteristic value, the second characteristic value and the third characteristic value corresponding to each characteristic dimension comprises: Obtaining a first difference amount corresponding to the i-th feature dimension according to the first eigenvalue and the third eigenvalue corresponding to the i-th feature dimension, where the first difference amount is equal to the third eigenvalue minus the first eigenvalue; Obtaining a second difference amount corresponding to the i-th feature dimension according to the second eigenvalue and the third eigenvalue corresponding to the i-th feature dimension, where the second difference amount is equal to the third eigenvalue minus the second eigenvalue; A characteristic trend indicator corresponding to the i-th characteristic dimension is obtained according to the first difference amount, the second difference amount and the third characteristic value.

3. The method for analyzing automobile finance customer behavior data based on artificial intelligence according to claim 2 is characterized in that: The characteristic trend index corresponding to the i-th characteristic dimension is obtained according to the first difference amount, the second difference amount and the third characteristic value as follows: T i =(ΔC i1 +ΔC i2 )·C i3 ;in, T i is the characteristic trend indicator corresponding to the i-th characteristic dimension, ΔC i1 is the first difference corresponding to the i-th feature dimension, ΔC i2 is the second difference corresponding to the i-th feature dimension, C i3 is the third eigenvalue corresponding to the i-th feature dimension.

4. The method for analyzing automobile finance customer behavior data based on artificial intelligence according to claim 1, characterized in that: The feature calculation model in obtaining the first feature value corresponding to each feature dimension based on the feature calculation model and the first behavior data is expressed as: C i1 =a i1 ·(ln(l i1 +c)+t i1 ); among them, C i1 is the first eigenvalue of the i-th feature dimension, α i1 is the adjustment coefficient of the i-th feature dimension in the first line of data, l i1 is the number of clicks on the i-th feature dimension in the first behavior data, t i1 is the browsing time of the i-th feature dimension in the first line of data, and γ is a preset parameter.

5. The method for analyzing automobile finance customer behavior data based on artificial intelligence according to claim 1, characterized in that: The feature calculation model in obtaining the second feature value corresponding to each feature dimension based on the feature calculation model and the second behavior data is expressed as: C i2 =a i2 ·(ln(l i2 +c)+t i2 ); among them, C i2 is the second eigenvalue of the i-th feature dimension, α i2 is the adjustment coefficient of the i-th feature dimension in the second line of data, l i2 is the number of clicks on the i-th feature dimension in the second behavior data, t i2 is the browsing time of the i-th feature dimension in the second behavior data, and γ is a preset parameter.

6. The method for analyzing automobile finance customer behavior data based on artificial intelligence according to claim 1, characterized in that: The feature calculation model in obtaining the third feature value corresponding to each feature dimension based on the feature calculation model and the third behavior data is expressed as: C i3 =a i3 ·(ln(l i3 +c)+t i3 ); among them, C i3 is the third eigenvalue of the i-th feature dimension, α i3 is the adjustment coefficient of the i-th feature dimension in the third line of data, l i3 is the number of clicks on the i-th feature dimension in the third behavior data, t i3 is the browsing time of the i-th feature dimension in the third behavior, and γ is a preset parameter.

7. The method for analyzing automobile finance customer behavior data based on artificial intelligence according to claim 1, characterized in that: The acquiring of first behavior data, second behavior data and third behavior data distributed in chronological order according to the behavior data comprises: According to the behavior data, the behavior start time point, the first behavior middle time point, the second behavior middle time point and the behavior end time point distributed in chronological order are obtained; Acquire a first time period according to the start time point of the behavior and the middle time point of the first behavior, and acquire the first behavior data corresponding to the first time period; Acquire a second time period according to the middle time point of the first behavior and the middle time point of the second behavior, and acquire the second behavior data corresponding to the second time period; A third time period is obtained according to the middle time point of the second behavior and the end time point of the behavior, and third behavior data corresponding to the third time period is obtained.

8. The method for analyzing automobile finance customer behavior data based on artificial intelligence according to claim 1, characterized in that: The acquiring of first behavior data, second behavior data, and third behavior data distributed in chronological order according to the behavior data includes: Obtain a time series based on the behavior data and set a first time window; Acquire a first time period, a second time period, and a third time period distributed in chronological order on the behavior time series according to the first time window; First behavior data corresponding to the first time period, second behavior data corresponding to the second time period, and third behavior data corresponding to the third time period are acquired according to the behavior data.

9. An artificial intelligence-based automobile finance customer behavior data analysis system, characterized in that: The system is used to implement the artificial intelligence-based automobile finance customer behavior data analysis method according to any one of claims 1 to 7, and the system comprises: An acquisition and generation module is used to acquire the behavior data of completed auto finance customers based on an artificial intelligence terminal, and acquire completed auto finance services based on the behavior data, and acquire multiple auto finance demands based on the completed auto finance services, and generate multiple feature dimensions based on the multiple auto finance demands; A data acquisition module, used for acquiring first behavior data, second behavior data and third behavior data distributed in chronological order according to the behavior data; A feature calculation module, used to obtain a first feature value corresponding to each feature dimension based on the feature calculation model and the first behavior data, obtain a second feature value corresponding to each feature dimension based on the feature calculation model and the second behavior data, and obtain a third feature value corresponding to each feature dimension based on the feature calculation model and the third behavior data; The analysis and processing module is used to obtain the characteristic trend index corresponding to each characteristic dimension according to the first characteristic value, the second characteristic value and the third characteristic value corresponding to each characteristic dimension, and obtain the push relationship between the automobile financial service and the behavior data according to each characteristic trend index.

10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the artificial intelligence-based automobile finance customer behavior data analysis method as described in any one of claims 1 to 7.

Images